Performance evaluation of cache depot on CC-NUMA multiprocessors

Hung-Chang Hsiao, Chung Ta King

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Cache depot is a performance enhancement technique on cache-coherent non-uniform memory access (CC-NUMA) multiprocessors, in which nodes in the system store extra memory blocks on behalf of other nodes. In this way, memory requests from a node can be satisfied by nearby depot nodes without going all the way to the home node. This not only reduces memory access latency and network traffic, but also spreads the network load more evenly. In this paper, we study the design strategy for cache depot that (1) enhances the network interface of each node to include a depot cache which stores those extra memory blocks for other nodes, and (2) employs a new multicast routing scheme, which is called the multi-hop worms and works cooperatively with depot caches, to transmit coherence messages. By considering message routing and depot caches together, the design concept can be applied even to those CC-NUMA systems that have a non-hierarchical, scalable interconnection network. We have developed an execution-driven simulator to evaluate the effectiveness of the design strategy. Performance results from using four SPLASH-2 benchmarks show that the design strategy improves the performance of the CC-NUMA multiprocessor by 11% to 21%. We have also studied in depth various factors which affect the performance of cache depot.

Original languageEnglish
Title of host publicationProceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS
EditorsC.N. Chen, L.M. Ni
PublisherIEEE Comp Soc
Pages519-526
Number of pages8
Publication statusPublished - 1998
EventProceedings of the 1998 International Conference on Parallel and Distributed Systems, ICPADS - Tainan, China
Duration: 1998 Dec 141998 Dec 16

Other

OtherProceedings of the 1998 International Conference on Parallel and Distributed Systems, ICPADS
CityTainan, China
Period98-12-1498-12-16

Fingerprint

Data storage equipment
Interfaces (computer)
Simulators

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture

Cite this

Hsiao, H-C., & King, C. T. (1998). Performance evaluation of cache depot on CC-NUMA multiprocessors. In C. N. Chen, & L. M. Ni (Eds.), Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS (pp. 519-526). IEEE Comp Soc.
Hsiao, Hung-Chang ; King, Chung Ta. / Performance evaluation of cache depot on CC-NUMA multiprocessors. Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS. editor / C.N. Chen ; L.M. Ni. IEEE Comp Soc, 1998. pp. 519-526
@inproceedings{fdb58a491ce84473ac1b4b64eefbea06,
title = "Performance evaluation of cache depot on CC-NUMA multiprocessors",
abstract = "Cache depot is a performance enhancement technique on cache-coherent non-uniform memory access (CC-NUMA) multiprocessors, in which nodes in the system store extra memory blocks on behalf of other nodes. In this way, memory requests from a node can be satisfied by nearby depot nodes without going all the way to the home node. This not only reduces memory access latency and network traffic, but also spreads the network load more evenly. In this paper, we study the design strategy for cache depot that (1) enhances the network interface of each node to include a depot cache which stores those extra memory blocks for other nodes, and (2) employs a new multicast routing scheme, which is called the multi-hop worms and works cooperatively with depot caches, to transmit coherence messages. By considering message routing and depot caches together, the design concept can be applied even to those CC-NUMA systems that have a non-hierarchical, scalable interconnection network. We have developed an execution-driven simulator to evaluate the effectiveness of the design strategy. Performance results from using four SPLASH-2 benchmarks show that the design strategy improves the performance of the CC-NUMA multiprocessor by 11{\%} to 21{\%}. We have also studied in depth various factors which affect the performance of cache depot.",
author = "Hung-Chang Hsiao and King, {Chung Ta}",
year = "1998",
language = "English",
pages = "519--526",
editor = "C.N. Chen and L.M. Ni",
booktitle = "Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS",
publisher = "IEEE Comp Soc",

}

Hsiao, H-C & King, CT 1998, Performance evaluation of cache depot on CC-NUMA multiprocessors. in CN Chen & LM Ni (eds), Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS. IEEE Comp Soc, pp. 519-526, Proceedings of the 1998 International Conference on Parallel and Distributed Systems, ICPADS, Tainan, China, 98-12-14.

Performance evaluation of cache depot on CC-NUMA multiprocessors. / Hsiao, Hung-Chang; King, Chung Ta.

Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS. ed. / C.N. Chen; L.M. Ni. IEEE Comp Soc, 1998. p. 519-526.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Performance evaluation of cache depot on CC-NUMA multiprocessors

AU - Hsiao, Hung-Chang

AU - King, Chung Ta

PY - 1998

Y1 - 1998

N2 - Cache depot is a performance enhancement technique on cache-coherent non-uniform memory access (CC-NUMA) multiprocessors, in which nodes in the system store extra memory blocks on behalf of other nodes. In this way, memory requests from a node can be satisfied by nearby depot nodes without going all the way to the home node. This not only reduces memory access latency and network traffic, but also spreads the network load more evenly. In this paper, we study the design strategy for cache depot that (1) enhances the network interface of each node to include a depot cache which stores those extra memory blocks for other nodes, and (2) employs a new multicast routing scheme, which is called the multi-hop worms and works cooperatively with depot caches, to transmit coherence messages. By considering message routing and depot caches together, the design concept can be applied even to those CC-NUMA systems that have a non-hierarchical, scalable interconnection network. We have developed an execution-driven simulator to evaluate the effectiveness of the design strategy. Performance results from using four SPLASH-2 benchmarks show that the design strategy improves the performance of the CC-NUMA multiprocessor by 11% to 21%. We have also studied in depth various factors which affect the performance of cache depot.

AB - Cache depot is a performance enhancement technique on cache-coherent non-uniform memory access (CC-NUMA) multiprocessors, in which nodes in the system store extra memory blocks on behalf of other nodes. In this way, memory requests from a node can be satisfied by nearby depot nodes without going all the way to the home node. This not only reduces memory access latency and network traffic, but also spreads the network load more evenly. In this paper, we study the design strategy for cache depot that (1) enhances the network interface of each node to include a depot cache which stores those extra memory blocks for other nodes, and (2) employs a new multicast routing scheme, which is called the multi-hop worms and works cooperatively with depot caches, to transmit coherence messages. By considering message routing and depot caches together, the design concept can be applied even to those CC-NUMA systems that have a non-hierarchical, scalable interconnection network. We have developed an execution-driven simulator to evaluate the effectiveness of the design strategy. Performance results from using four SPLASH-2 benchmarks show that the design strategy improves the performance of the CC-NUMA multiprocessor by 11% to 21%. We have also studied in depth various factors which affect the performance of cache depot.

UR - http://www.scopus.com/inward/record.url?scp=0032300644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032300644&partnerID=8YFLogxK

M3 - Conference contribution

SP - 519

EP - 526

BT - Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS

A2 - Chen, C.N.

A2 - Ni, L.M.

PB - IEEE Comp Soc

ER -

Hsiao H-C, King CT. Performance evaluation of cache depot on CC-NUMA multiprocessors. In Chen CN, Ni LM, editors, Proceedings of the Internatoinal Conference on Parallel and Distributed Systems - ICPADS. IEEE Comp Soc. 1998. p. 519-526